experience-app-mcp-delivery-generate

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the official Salesforce CLI (sf) to perform discovery and metadata retrieval. This is a primary function of the tool and uses validated inputs to mitigate injection risks.
  • [DYNAMIC_EXECUTION]: The packaging logic in generate_plugin.mjs includes a blacklist for sensitive file types (e.g., .env, .pem, .key, .sf) when bundling skills, protecting against accidental secret exposure in generated repositories.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external metadata and SKILL.md files to generate plugin documentation. It includes instructions for the user to review the generated output before publication, which serves as a mitigation for potential malicious content in processed inputs.
  • [SAFE]: The implementation demonstrates high security awareness by explicitly avoiding the retrieval or logging of sensitive data. Scripts are programmed to ignore access tokens, consumer secrets, and refresh tokens, focusing solely on public identifiers like client IDs.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 10:15 PM